From 713bafea92920103cd3d361657406cf04d0e22dd Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 8 Nov 2017 13:01:26 -0800 Subject: tcp: retire FACK loss detection FACK loss detection has been disabled by default and the successor RACK subsumed FACK and can handle reordering better. This patch removes FACK to simplify TCP loss recovery. Signed-off-by: Yuchung Cheng Reviewed-by: Eric Dumazet Reviewed-by: Neal Cardwell Reviewed-by: Soheil Hassas Yeganeh Reviewed-by: Priyaranjan Jha Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'net/ipv4/tcp_minisocks.c') diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bb86580decd..326c9282bf94 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -509,10 +509,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, keepalive_time_when(newtp)); newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; - if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) { - if (sock_net(sk)->ipv4.sysctl_tcp_fack) - tcp_enable_fack(newtp); - } + newtp->rx_opt.sack_ok = ireq->sack_ok; newtp->window_clamp = req->rsk_window_clamp; newtp->rcv_ssthresh = req->rsk_rcv_wnd; newtp->rcv_wnd = req->rsk_rcv_wnd; -- cgit